© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 227245
    Prev
    Next
    INDEX
    Explanations

    expect expert advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    moid
    0.46
    RestorePolicy
    0.45
    צוני
    0.45
    ynthia
    0.44
    тия
    0.42
    ▬▬
    0.42
    зумі
    0.42
    ере
    0.42
    фектив
    0.42
    образова
    0.41
    POSITIVE LOGITS
    u
    0.50
     proposer
    0.44
     Messe
    0.43
    꾼
    0.43
     supercar
    0.43
     Bila
    0.41
     notifying
    0.41
     attacking
    0.41
     जंग
    0.41
     advertiser
    0.41
    Activations Density 0.001%

    No Known Activations